@@ -1,6 +1,6 @@
 Package: MSTExplorer
 Title: Multi-Scale Target Explorer
-Version: 1.0.9
+Version: 1.0.10
 Authors@R:
     c(
     person(given = "Brian",
@@ -30,7 +30,7 @@ Encoding: UTF-8
 URL: https://github.com/neurogenomics/MSTExplorer
 BugReports: https://github.com/neurogenomics/MSTExplorer/issues
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 Depends: 
     R (>= 4.1)
 Imports:
@@ -77,7 +77,8 @@ Suggests:
     tibble,
     tidytext,
     ggrepel,
-    gtools
+    gtools,
+    ggrastr
 Remotes: 
   github::neurogenomics/HPOExplorer,
   github::neurogenomics/KGExplorer,
 
@@ -1,16 +1,19 @@
 # Generated by roxygen2: do not edit by hand
 
 export(add_ctd)
+export(add_driver_genes)
 export(add_logfc)
 export(add_symptom_results)
 export(agg_results)
 export(correlation_heatmap)
 export(create_dt)
 export(ewce_para)
+export(filter_ggstatsplot_subtitle)
 export(gen_overlap)
 export(gen_results)
 export(get_bg)
 export(get_cl)
+export(get_replication_rate)
 export(get_unfinished_list_names)
 export(ggnetwork_plot_full)
 export(load_example_ctd)
@@ -37,6 +40,7 @@ export(prioritise_targets_grid)
 export(prioritise_targets_multiheatmap)
 export(prioritise_targets_network)
 export(run_congenital_enrichment)
+export(run_permutation_test_cor)
 export(run_phenomix)
 export(subset_phenos)
 export(subset_results)
@@ -51,12 +55,15 @@ import(HPOExplorer)
 import(KGExplorer)
 import(data.table)
 import(ggplot2)
+importFrom(BiocParallel,MulticoreParam)
+importFrom(BiocParallel,bplapply)
 importFrom(EWCE,bootstrap_enrichment_test)
 importFrom(HPOExplorer,add_ancestor)
 importFrom(HPOExplorer,add_gene_frequency)
 importFrom(HPOExplorer,get_gene_lists)
 importFrom(HPOExplorer,load_phenotype_to_genes)
 importFrom(data.table,":=")
+importFrom(data.table,data.table)
 importFrom(data.table,fread)
 importFrom(data.table,melt)
 importFrom(data.table,rbindlist)
@@ -71,7 +78,9 @@ importFrom(plotly,ggplotly)
 importFrom(scales,pretty_breaks)
 importFrom(stats,as.formula)
 importFrom(stats,complete.cases)
+importFrom(stats,cor)
 importFrom(stats,dist)
+importFrom(stats,quantile)
 importFrom(stats,setNames)
 importFrom(stringr,str_replace_all)
 importFrom(stringr,str_wrap)
 
@@ -1,3 +1,13 @@
+# MSTExplorer 1.0.10
+
+## New features
+* `run_permutation_test_cor`: New function to run permutation tests.
+* `plot_ontology_levels`: Add more args. Make "info_content_binned" 
+  a separate col from raw "info_content".
+
+## Bug fixes
+* Update all calls to `facet_grid` to not use deprecated `facets` arg.
+
 # MSTExplorer 1.0.9
 
 ## New features
 
@@ -21,6 +21,7 @@
 #' @param subtitle_size Size of the plot subtitle.
 #' @param phenotype_to_genes Phenotype to gene mapping from
 #' \link[HPOExplorer]{load_phenotype_to_genes}.
+#' @param dpi Resolution of image after rasterization.
 #' @family plot_
 #' @returns R object.
 #' @name plot_
 
@@ -2,11 +2,11 @@
 #'
 #' Annotate genes in \code{results} with data from a CellTypeDataset (CTD).
 #' The following columns will be added:
-#' \itemize{
-#' \item{"specificity"} Cell-type specificity score.
-#' \item{"specificity_quantiles"} Cell-type specificity quantile.
-#' \item{"mean_exp"} Mean expression per cell-type.
-#' \item{"mean_exp_quantiles"} Mean expression quantile per cell-type.
+#' \describe{
+#' \item{"specificity"}{Cell-type specificity score.}
+#' \item{"specificity_quantiles"}{Cell-type specificity quantile.}
+#' \item{"mean_exp"}{Mean expression per cell-type.}
+#' \item{"mean_exp_quantiles"}{Mean expression quantile per cell-type.}
 #' }
 #' @param keep_celltypes A character vector of cell types to keep.
 #' @inheritParams ewce_para
 
@@ -1,10 +1,29 @@
+#' Add driver genes
+#'
+#' This function identifies "driver genes" from phenotype-cell type association analyses.
+#' For a given phenotype-cell type pair, driver genes are defined as the intersect of genes that had a
+#' phenotype evidence score >0 and were within the top 75th expression specificity percentile
+#' (quantiles 30-40 out of 40) for the associated cell type.
+#'
+#' @param min_value Miniumum specificity quantile to keep.
+#' @param metric Which metric to use in the CellTypeDatasets.
+#' @param group_var Grouping variable to use when selecting top N genes.
+#' Only used when \code{top_n!=NULL}.
+#' @param celltype_var The name of the cell type column to merge on.
+#' @inheritParams prioritise_targets
+#' @inheritParams add_symptom_results
+#' @inheritDotParams HPOExplorer::add_genes
+#' @export
+#' @examples
+#' res <- load_example_results()[seq(100)]
+#' res <- add_driver_genes(results=res)
 add_driver_genes <- function(results = load_example_results(),
                              ctd_list = load_example_ctd(
                                file = paste0("ctd_",unique(results$ctd),".rds"),
                                multi_dataset = TRUE
                                ),
                              annotLevels = map_ctd_levels(results),
-                             keep_quantiles = NULL,
+                             keep_quantiles = seq(30,40),
                              min_value = NULL,
                              metric = "specificity_quantiles",
                              top_n = NULL,
 
@@ -35,7 +35,7 @@ add_symptom_results <- function(results = load_example_results(),
                                 ){
   n_genes_hpo_id <- n_genes_disease_id <- n_genes_symptom <- gene_symbol <-
     celltype_symptom <- n_driver_genes_symptom <-
-    proportion_driver_genes_symptom <- NULL;
+    proportion_driver_genes_symptom <- ..merge_cols <- NULL;
 
   if("proportion_driver_genes_symptom" %in% names(results)){
     messager("Symptom results already present in input.")
 
@@ -16,27 +16,37 @@
 #' phenos <- subset_results(filters = list(CellType="Microglia"))
 #' agg_res <- agg_results(phenos = phenos)
 agg_results <- function(phenos,
-                        count_var = "hpo_name",
+                        count_var = "hpo_id",
                         group_var = "CellType",
                         sep="; ",
                         verbose = TRUE){
-  effect <- sd_from_mean <- . <- gene_symbol <- NULL;
+  estimate <- std.error <- sd_from_mean <- . <- gene_symbol <- NULL;
+
+
+  group_var <- group_var[group_var %in% names(phenos)]
+  if("sd_from_mean" %in% names(phenos)){
+    phenos$std.error <- phenos$sd_from_mean
+  }
+
   messager("Aggregating results by",
            paste0("group_var=",paste(shQuote(group_var),collapse = "/")),
            v=verbose)
+
   phenos <- HPOExplorer::add_hpo_name(phenos)
+
   #### Aggregate ####
-  counts_df <- unique(phenos[,.(
+  counts_df <- unique(
+    phenos[,.(
     count=data.table::uniqueN(eval(parse(text = count_var))),
     n_genes=if("gene_symbol" %in% names(phenos)) {
       data.table::uniqueN(gene_symbol,na.rm = TRUE)
     } else NA,
     genes=if("gene_symbol" %in% names(phenos)){
       paste(unique(gene_symbol),collapse = sep)
     } else NA,
-    mean_effect=round(mean(effect),3),
+    mean_estimate=round(mean(estimate),3),
     mean_q=round(mean(q),3),
-    mean_sd_from_mean=round(mean(sd_from_mean),3),
+    mean_std.error=round(mean(std.error),3),
     values=paste(
       stringr::str_wrap(paste(unique(eval(parse(text = count_var))),
                               collapse = sep)),
@@ -46,10 +56,11 @@ agg_results <- function(phenos,
                    "count",
                    "n_genes",
                    "genes",
-                   "mean_effect",
+                   "mean_estimate",
                    "mean_q",
-                   "mean_sd_from_mean",
-                   "values"), with=FALSE])
+                   "mean_std.error",
+                   "values"), with=FALSE]
+  )
   data.table::setnames(counts_df,
                        c("count","values"),
                        c(paste("n",paste0(tolower(count_var),"s"),sep="_"),
 
@@ -3,6 +3,7 @@ construct_labeller <- function(dat,
                                facets_n,
                                suffix="phenotypes"){
   facet_label <- NULL;
+  dat <- data.table::copy(dat)
   if(is.null(facets_n) ||
      !facets_n %in% names(dat)) {
     "label_value"
 
@@ -7,17 +7,23 @@ extract_filters <- function(pkg = "MSTExplorer",
   out <- extract_help(pkg = pkg,
                       fn = fn,
                       to = "html")
-  filters <- (
-    rvest::read_html(paste(out,collapse = "")) |>
-      rvest::html_elements("ol")
-  )[[1]] |>
-    rvest::html_children() |>
-    rvest::html_text() |>
-    stringr::str_split(":",n = 3, simplify = TRUE) |>
-    data.table::as.data.table() |>
+
+  txt <- (rvest::read_html(paste(out,collapse = ""))|>
+    rvest::html_elements("dl"))[[1]] |>
+    rvest::html_children()|>
+    rvest::html_text()
+
+  filters <- data.table::data.table(
+    stringr::str_split(txt[seq(from = 1, to = length(txt)-1, by = 2)] ,"; ",
+                       n = 2,
+                       simplify = TRUE)[,c(1,2)],
+    txt[seq(from = 2, to = length(txt), by = 2)]
+  )|>
     `colnames<-`(c("level","step","description"))
+
   cols <- names(filters)
   filters[ , (cols) := lapply(.SD, trimws), .SDcols = cols]
+  filters[ , (cols) := lapply(.SD, trimws, whitespace=";"), .SDcols = cols]
   filters[,level:=gsub("[-]|level|levels","",level)]
   #### Print for plot legend ####
   # cat(paste(filters[,legend:=paste0(step,": ",description)]$legend, collapse = "\n"))